Agentcap — Productivity skill for Claude Code
A hard, real-time dollar cap on Claude Code sessions — so a runaway agent can't burn an unexpected bill.
How to install Agentcap
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open manan4641/agentcap and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Agentcap does
**A hard, real-time dollar cap on Claude Code sessions — so a runaway agent can't burn an unexpected bill.**
Alternatives in Productivity
- Tradingview MCP — Real-time crypto & stock screening, advanced technical indicators, Bollinger Bands intelligence, candlestick p 2.6k ★
- GrokSearch — Integrate Grok's powerful real-time search capabilities into Claude via the MCP protocol 1.8k ★
- Claude Code Hooks Multi Agent Observability — Real-time monitoring for multi-agent Claude Code sessions via hook event tracking 1.3k ★
README
AgentCap
**A hard, real-time dollar cap on Claude Code sessions — so a runaway agent can't burn an unexpected bill.**
Free for individuals on their own personal work, source-available, and entirely local. No account, no signup, no telemetry, no network calls. Company and team use needs a [commercial licence](#licence).
agentcap run --cap 5.00 -- claude
Warns you at 80% of the cap. Terminates the session at 100%. Logs every session to a local SQLite file you own.
Install
npm install -g @oneclickera/agentcap
Or run it without installing:
npx @oneclickera/agentcap run --cap 5.00 -- claude
Requires Node 20 or newer.
If you get `agentcap: command not found` after installing
This almost always means npm's global bin directory isn't on your shell's `PATH`. It's common with nvm, whose setup usually lives in `.zshrc` — so if your login shell is **bash** (or you have no bash dotfiles), the shell never loads nvm and never sees `agentcap`, `npm`, or even `node`.
Check where npm installed it and whether your shell can see that directory:
npm prefix -g # npm's global bin lives in /bin
echo $PATH
The most reliable fix is a small launcher in a directory that's always on `PATH`, which calls node by absolute path instead of relying on `#!/usr/bin/env node`:
printf '#!/bin/sh\nexec "%s" "%s" "$@"\n' "$(command -v node)" "$(npm prefix -g)/lib/node_modules/@oneclickera/agentcap/bin/agentcap.js" \
> /usr/local/bin/agentcap && chmod +x /usr/local/bin/agentcap
AgentCap also resolves the *agent* binary the same way — it checks `~/.local/bin`, `~/bin`, `~/.claude/local`, `/usr/local/bin`, and `/opt/homebrew/bin` before giving up, so `-- claude` keeps working even when Claude Code isn't on your `PATH`.
Usage
# Wrap a normal interactive Claude Code session with a $5 cap
agentcap run --cap 5.00 -- claude
# `claude` is the default, so this is the same thing
agentcap run
Related Skills
Claude Code Usage Bar
Real‑time statusline for Claude Code: token usage, remaining budget, burn rate, and depletion time.
Cc Aio Mon
Real-time terminal monitor for Claude Code — context window, rate limits, costs, burn rate. Stdlib only.
Paynow Billpay Skill
A Claude skill for integrating Paynow BillPay: vend ZESA tokens, airtime and bill payments without double-char
Codync
A real-time companion for Claude Code — monitor your coding sessions from anywhere, on any Apple device.
Observagent
Zero-config observability for Claude Code agent sessions Track costs, monitor tool usage, analyze latency, and
Claude Code Dashboard
A lightweight localhost dashboard that monitors multiple Claude Code sessions in real-time. See token usage, c
Related Agents
Systems Architect
Use this agent when you need real-time systems architecture, ultra-low latency design, or deterministic system
Polymathic Gates
Reasons through Bill Gates's cognitive architecture — platform thinking, systematic deep-reading, multi-source
Omd Final QA
Read-only final-gate critic. Enforces an 8-item rubric. Hard 2-round revision cap. Forbids 'looks good' rubber